|
|
|
| 3D Reconstruction of Human Body Based on Orthogonal Matching Pursuit and Accelerated Proximal Gradient |
| Wang Yaming, Zhai Junpeng, Mo Yan*, Han Yonghua, Jiang Mingfeng |
| Research Institute of Signal and Information Processing, Zhejiang Sci-tech University, Hangzhou 310018, China |
|
|
|
|
Abstract In order to improve the reconstruction accuracy of the 3D structure of human body, the optimal selection of atoms and the optimization of structure matrix in the process of reconstruction were investigated in this work. On the basis of the sparse representation and low-rank constraint, we proposed anorthogonal matching pursuit and accelerated proximal gradient (OMP-APG) algorithm to provide a wealth information to assist medical doctors to work out the treatment plan quickly and accurately. First of all, the feature matrix was decomposed by singular value decomposition (SVD), and the uniquely determined camera rotation matrix was obtained by LM (Levenberg-Marquardt) algorithm. Secondly, according to the idea of “maximization approximation” in sparse representation, the trajectory basis coefficients were solved by orthogonal matching pursuit algorithm, combined with a predefined trajectory basis to solve the 3D structure of the human body matrix. Finally, considering that the structure matrix was a low rank matrix, the rank optimization problem was transformed into the nuclear norm minimization problem, and the human body structure matrix was further optimized by the accelerated proximal gradient algorithm. The algorithm and sparse approximation algorithms were compared in five motion models including stretch, yoga, pick up, drink and dance in 3D reconstruction with the 3D reconstruction renderings and 3D reconstruction errors. The results showed that the reconstruction accuracy was higher and had better stability. In this algorithm, the reconstruction of drink motion was the best, and the reconstruction error of the 41 feature points of the 1102 frame image sequence was about 0.0303, while the reconstruction error under the sparse algorithm was about 0.0178. In conclusion, the algorithm improved the reconstruction accuracy of the human three-dimensional structure.
|
|
Received: 27 September 2016
|
|
|
|
|
|
[1] Fabio R. 3-D reconstruction of static human body shape from image sequence[J]. Computer Vision and Image Understanding, 2004, 93(1): 65-85.
[2] Moeslund TB, Granum E. A survey of computer vision-based human motion capture[J]. Computer Vision and Image Understanding, 2001, 81(3): 231-268.
[3] Tmoasi C, Kanade T. Shape and motion from image streams under orthography: a factorization method[J]. International Journal of Computer Vision, 1992, 9(2): 137-154.
[4] Bregler C, Hertzmann A, Biermann H. Recovering non-rigid 3D shape from image streams[C] //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Hilton Head: IEEE, 2000, 2: 690-696.
[5] Akhter I, Sheikh Y, Khan S, et al. Trajectory space: A dual representation for nonrigid structure from motion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(7): 1442-1456.
[6] Barthelemy Q, Larue A, Mars J. Decomposition and dictionary learning for 3D trajectories[J]. Signal Processing, 2014, 98: 423-437.
[7] Zhu Yingying, Simon L. Convolutional sparse coding for trajectory reconstruction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 529-540.
[8] Park HS, Shiratori T, Matthews I, et al. 3D reconstruction of a moving point from a series of 2D projections[C] //2010 IEEE European Conference on Computer Vision. Berlin: Springer-Verlag, 2010, 6313: 158-171.
[9] Park SH,Shiratori T, Matthews I, et al. 3D trajectory reconstruction under perspective projection[J]. International Journal of Computer Vision, 2015, 115(2): 115-135.
[10] Bue AD, Smeraldi F, Agapito L. Non-rigid structure from motion using non-parametric tracking and non-linear optimization[C] //2004 Conference on Computer Vision and Pattern Recognition Workshop(CVPRW). Washington: IEEE, 2004: 8-8.
[11] Zhu Yingying, Cox M, Simon L. 3D motion reconstruction for real-world camera motion[C] //2011 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Colorado Springs: IEEE, 2011, 8: 1-8.
[12] Vore D, Ronald A. Nonlinear approximation[J]. Acta Numerica, 1998, 7: 51-150.
[13] Mallat S, Zhang Zhifeng. Matching pursuits with time-frequency dictionaries[J]. IEEE Transactions on Signal Processing, 1993, 41(12): 3397-3415.
[14] Pati Y, Rezaiifar R, Krishnaprasad PS. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition[C] //Proceedings of 27th Asilomar Conference on Signals, Systems and Computers. Los Alamitos: IEEE, 1993: 40-44.
[15] Wang Yaming, Yan Xiaomeng, ZhengJ B, et al. Sparse approximation for nonrigid structure from motion[J]. Journal of Robotics, 2015, 3: 1-8.
[16] Chen Mingyu, Alergib G, Juang BH. Trajectory triangulation: 3D motion reconstruction with 1 optimization[C] //2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague: IEEE, 2011: 4020-4023.
[17] Sahoo S, Makur A. Signal recovery from random measurements via extended orthogonal matching pursuit[J]. IEEE Transactions on Signal Processing, 2015, 63(10): 2572-2581.
[18] Silvia G, Isao Y. Alternating minimization techniques for the efficient recovery of a sparsely corrupted low-rank matrix[C] //2010 IEEE International Conference on Acoustics, Speech and Signal Processing. Dallas: IEEE, 2010, 6: 3638-3641.
[19] Trémoulhéac B, Atkinson D, Arridge SR. Fast dynamic MRI via nuclear norm minimization and accelerated proximal gradient[C] //2013 IEEE 10th International Symposium on Biomedical Imaging. San Francisco: IEEE, 2013: 322-325.
[20] Yue Lu, Zhang Liwei. The augmented Lagrangian method based on the APG strategy for an inverse damped gyroscopic eigenvalue problem[J]. Computational Optimization and Applications, 2015, 62(3): 815-850.
[21] Wang Yaming, Tong Lingling, Jiang Mingfeng, et al. Non-rigid structure estimation in trajectory space from monocular vision[J]. Sensors, 2015, 15(10): 25730-25745.
[22] Paladini M, Del Bue A, Stosic M, et al. Factorization for non-rigid and articulated structure using metric projections[C] //2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Miami: IEEE, 2009: 2898-2905. |
|
|
|
